Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Knowingly Wrong

https://knowingly-wrong.github.io/
knowingly-wrong
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

sohv  authored a paper 10 days ago
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
mollejasaurio  authored a paper 15 days ago
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
mollejasaurio  updated a dataset 16 days ago
knowingly-wrong/realistic-data
View all activity

Papers

Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment

View all Papers

Guido Freire's profile picture Sohan Venkatesh's profile picture Ariana Mirella Villegas Suarez's profile picture
Organization Card
Community About org cards

knowingly-wrong

Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywiński

Adapters and datasets developed during the LASR Labs fellowship to reproduce experiments and figures from Knowingly Wrong: Training LLMs Against Their Own Beliefs can Cause Misalignment.

Structure

wrongness/

persona-vectors/

realistic-scenarios/

models 3

knowingly-wrong/realistic-scenarios

Updated 16 days ago

knowingly-wrong/persona-vectors

Updated 16 days ago

knowingly-wrong/wrongness

Updated 16 days ago

datasets 2

knowingly-wrong/realistic-data

Viewer • Updated 16 days ago • 97.2k • 84

knowingly-wrong/wrongness

Preview • Updated 16 days ago • 120
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs